International Journal of Science, Engineering and TechnologyAuthors: Mrs.S.Kalaiselvi., Mrs.J.Sneha .
Abstract: – Blood group identification is vital in medical contexts like emergencies, transfusions, and organ transplants. Traditional detection methods typically require invasive blood sampling and lab analysis, which can be time-consuming. To address these challenges, this project introduces a deep learning-based system for determining blood groups using fingerprint images, eliminating the need for physical blood samples. Utilizing Convolutional Neural Networks (CNN) alongside EfficientNet-B0, the model captures subtle fingerprint features linked to specific blood types. Trained on a labeled dataset of fingerprint images, the system learns to associate unique fingerprint patterns with corresponding blood groups. EfficientNet-B0’s optimized architecture ensures precise feature extraction with minimal computational cost. Once a blood type is identified, the system offers tailored health insights, including dietary suggestions, donor compatibility, and preventive measures. This innovative, non-invasive solution enables fast and reliable blood group detection, especially valuable in rural or emergency settings, enhancing accessibility and efficiency in modern healthcare.
DOI: http://doi.org/
